Worksnaps for AI agents

Worksnaps tracks time and activity for remote teams, used by managers who need visibility into project progress without being in the same room. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

HR and recruitingAPI keyMCP + RESTworksnaps.com
AUDIT LOG · WORKSNAPSPOLICY: acme-support
09:41:07 · claude · u_8f2read
worksnaps.get_tasks
Get Project Tasks✓ allowed · 212ms
09:41:08 · claude · u_8f2read
worksnaps.get_users
Get Users✓ allowed · 164ms
09:41:09 · claude · u_8f2write
worksnaps.create_task
Create task✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
worksnaps.delete_task
Delete Task✕ blocked · policy: deny
EVERY WORKSNAPS CALL, ON THE RECORD
01 · USE CASES

What agents do in Worksnaps.

01

Get a project's report

Pull tracked time and activity for a project, a read-only summary.

02

Create a new task

Add a task to a project for a team member to log time against.

03

Confirm before deleting a task

Check with the user before deleting a task, since its logged time entries reference it.

02 · ACTIONS

14 Worksnaps actions, graded by risk.

Every Worksnaps action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

8

Look things up. Allowed by default.

  • worksnaps.get_tasks
    Get Project Tasks
  • worksnaps.get_users
    Get Users
  • worksnaps.get_projects
    Get Projects
  • worksnaps.get_task_details
    Get Task Details
  • worksnaps.get_user_account
    Get User Account
  • worksnaps.get_project_report
    Get Project Report
  • worksnaps.get_project_details
    Get Project Details
  • worksnaps.get_user_assignments
    Get User Assignments

write

5

Create and change things. Allow, or ask the user first.

  • worksnaps.create_task
    Create task
  • worksnaps.create_project
    Create Project
  • worksnaps.put_update_task
    Update Task
  • worksnaps.put_update_project
    Update Project
  • worksnaps.put_update_user_account
    Update User Account

destructive

1

Delete, cancel or archive. Ask first, or deny outright.

  • worksnaps.delete_task
    Delete Task
03 · HOW IT WORKS

Worksnaps in three steps.

  1. 01Your users connect WorksnapsThey add their Worksnaps api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “create task” can wait for the user, and “delete Task” can be denied outright.
  3. 03Any agent can actYour agent calls Worksnaps through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('worksnaps', {
  read: 'allow',
  write: 'ask',        // create_task
  destructive: 'deny',  // delete_task
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How Worksnaps connects.

Users add their Worksnaps api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same Worksnaps connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH
API key
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use Worksnaps from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
07 · FAQ

Worksnaps and Arc0, answered.

Q01

Can I use Worksnaps with Claude, ChatGPT or Cursor?

Yes. Connect Worksnaps to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Worksnaps actions you allow.

Q02

How do users connect Worksnaps?

Users add their Worksnaps api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which Worksnaps actions can my agent take?

14 in total: 8 read, 5 write and 1 destructive, such as “create task”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Worksnaps?

Yes. Actions like “delete Task” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.

Q05

Can my own backend call Worksnaps too?

Yes. The same Worksnaps connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Worksnaps into your agent.

Your users connect Worksnaps once, under your brand. Your agent gets 14 actions behind your policies, with every call on the record.

Free to build · MCP + REST · Audit log on every plan